info presentación miembros líneas investigación publicaciones investigación tesis docencia

[Articulos Revista] [Articulos Congreso] [Reports] [Libros] [Capitulos Libro] [Todo] [Resumen]

Categoria WoS
  • Artificial Neural Networks
  • Genetic Programming
Titulo: Automatic recurrent ANN rule extraction with Genetic programming
Tipo: congreso internacional
Congreso: International Joint Conference on Neural Networks (IJCNN 2002)
Fecha: 12-17/5/2002
Lugar celebracion: Hawai, Honolulu (EEUU)
Paginas: 1552-1558
ISBN: 0-7803-7278-6
Libro: Proceeding Of The 2002 International Joint Conference On Neural Networks, Vols 1-3
Editorial: I E E E


Various rule-extraction techniques using ANNs have been used so far, most of them being applied on multi-layer ANNs, since they are more easily handled. In many cases, extraction methods focusing on different types of networks and training have been implemented, however, there are virtually no methods that view the extraction of rules from ANNs systems wich are independent from their architecture, training and internal distribution of weights, connections and activation functions. This paper proposes a rule extraction system of ANNs regardless of their architecture (multi-layer or recurrent), using Genetic programming as a rule-exploration technique

    .: SABIA :.  Sistemas Adaptativos y Bioinspirados en Inteligencia Artificial